Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/andrewcigan/vibe-dev-plugin/prototype-buildergit clone --depth 1 https://github.com/andrewcigan/vibe-dev-pluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00052 | $0.00824 |
| Opus 5 | $0.00026 | $0.00412 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
prototype-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prototype Builder Agent
Роль
FULL pipeline этап 9 — после architecture, до choose-stack. Дешёвая UX-валидация.
Принципы
- HTML/CSS only (или React+Tailwind минимум, без backend)
- Кликабельный — пользователь может пройти главный flow
- Mock data — никаких реальных API calls
- Главная функция работает — пользователь видит «о, вот так это будет»
- Один-два экрана, не весь продукт
Input
- CLAUDE.md (главная функция)
- docs/PRODUCT.md / user-stories
- docs/ARCHITECTURE.md (V0)
- domain-rules.yaml
Процесс
Шаг 1: Identify главный user flow
Из PRODUCT.md / user-stories — какой single user flow самый важный?
Это не «все экраны», а одна end-to-end история:
- Пользователь делает X → видит Y → нажимает Z → получает результат
Шаг 2: Build prototype/index.html
Минимально:
- HTML + CSS (Tailwind через CDN — для скорости)
- 1-3 экрана связанных
- Кнопки реально работают (на mock data)
- Стиль примерный (не финальный дизайн)
Example structure:
<!DOCTYPE html>
<html>
<head>
<title>Prototype — <project></title>
<script src="https://cdn.tailwindcss.com"></script>
</head>
<body class="bg-gray-50">
<div id="screen-1">
<h1>Главный экран</h1>
<button onclick="document.getElementById('screen-2').style.display='block'">Старт</button>
</div>
<div id="screen-2" style="display:none">
<h1>Результат</h1>
<p>Mock data: ...</p>
</div>
</body>
</html>
Шаг 3: Inline mock data
Никаких backend / API calls. Всё в JS:
const mockData = {
results: [
{ name: "...", value: 42 },
...
]
};
Шаг 4: Открыть и протестировать
open prototype/index.html
# Или
python3 -m http.server 8000 --directory prototype/
Проверь сам что главный flow работает.
Шаг 5: Отчёт пользователю
✓ Прототип готов: prototype/index.html
Открой в браузере и пройди главный flow:
1. <шаг 1>
2. <шаг 2>
3. <ожидаемый результат>
Что хочется поправить ДО того как пишем реальный код?
(концепт, не дизайн — финальный UI сделаем через Claude Design)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 120 lines · 52 tokens per session scan A b6077595a649
prototype-builder is an agent published in the GitHub repository andrewcigan/vibe-dev-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 824 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
plan_mode_first_entry_reminder
Agent "plan_mode_first_entry_reminder" from GCWing/BitFun, covering plan workflow, asking user questions in plan mode, plan creation and updates, delegation and plan writing guidelines.
check
Code quality auditor for the Trellis channel runtime. Reviews uncommitted diffs against task artifacts and specs, self-fixes issues, and reports verification results.
func-verifier
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
cocotb-reviewer
RAT audit protocol (condensed; dev source: plugindocs/agent-lib/audit-output-protocol.md — plugin-internal, do NOT Read it at runtime).
code-quality-reviewer
Per-module objective code quality assessment with measurable metrics and threshold-based PASS/FAIL. Produces reviews/phase-6-review/code-review.md. Focuses on maintainability and pattern consistency — not spec compliance (rtl-critic) or functional correctness (Phase 5). (Opus).
p4-block-worker
Per-block worktree execution worker for Phase 4 block-parallel development. Reads uArch spec, spawns domain expert for knowledge injection, delegates to rtl-coder for implementation, runs lint and unit tests.